# neural-maze/ava-whatsapp-agent-course

Meet Ava, the WhatsApp Agent

Repository: https://github.com/neural-maze/ava-whatsapp-agent-course
Canonical: https://ross.abutalabs.com/products/ava-whatsapp-agent-course
Language: Python
License: MIT
License Family: permissive
Topics: agent, agent-based, agentic-workflow, agents, stt, tts, vector-database
Last push: 2025-10-20T19:12:20+00:00

## Health v2 (maintenance only)
Score: 43/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 48, release rhythm 35, longevity 44
- inputs: {"age_days": 624, "days_push": 317, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1673, forks 419 (observed 2026-08-28T04:05:20.307269+00:00)

## What it is
Ava is a course project and codebase for building a WhatsApp AI agent that chats realistically, understands voice and images, and replies with voice notes and images. It doubles as a hands-on tutorial on agentic workflows with STT, TTS, and a vector database.

## Use cases
- build a whatsapp ai agent
- learn to build agentic workflows
- create a chatbot that answers voice messages
- send voice notes from an llm agent
- integrate stt and tts into an agent
- give an ai agent memory with a vector database
- make an ai companion that chats on whatsapp

## When to choose
- you want a guided, project-based course on building multimodal AI agents
- you need a working reference implementation of a WhatsApp voice-and-image agent in Python
- you are learning how STT, TTS, and vector databases fit into agentic systems

## When to avoid
- you need a production-ready, supported WhatsApp bot framework
- you want a library to drop into an existing app rather than a course codebase
- you need agents on platforms other than WhatsApp

## Facets
- artifact type: learning-resource
- maturity: active
- function: agent-framework, speech-recognition, tts, chatbot, rag, llm-inference
- domain: chatbots, large-language-models, tutorials, messaging-platforms
- platform: python, self-hosted
- tags: whatsapp-agent, agentic-workflow, voice-agent, multimodal-ai, course-project, ex-machina-inspired, ai-agents

## Member repositories
- neural-maze/ava-whatsapp-agent-course (main) score 43

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:20.307269+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:42:35.607763+00:00, confidence not recorded.
  - readme: https://github.com/neural-maze/ava-whatsapp-agent-course (fetched 2026-08-28T04:05:20.307269+00:00, sha cc24618e8400)
- Data as of 2026-08-30T08:39:29.467469+00:00.